HNHacker News
TopNewBestAskShowJobs

dwa3592

1,029 karma · joined June 23, 2025

Could I get some extra humor on the side please? Thanks.
submissionscomments
dwa3592··on NotebookLM is now Gemini Notebook
Antigravity sucks so bad that I have started to feel that google really doesn't wanna compete, they just wanna hang in there at number 2 or 3, to just annoy the number 1 and 2.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
glad to know. thanks :)
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
dario has been saying open source models are dangerous. who knows who is listening to him.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
Its really easy to argue against local models because when it comes to quality, you can argue using the tokens/sec. and when it comes to speed, you can argue using the parameter count. This is not compared to the frontier stuff but it is the frontier of last year that now runs on a local machine. It was impossible to do this last year.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
It will, but the process at this point is SSD bound rather than compute bound. On a bigger machine, Apple silicon must help but I don't have a bigger machine. I can think about this more and will make changes if that helps.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
>>Yes, it’s technically running, but not in a way that would be useful by normal LLM standards.

What are the LLM standards?

Do you know how many people use perplexity? I know many people who are not software engineers or tech workers and have a LLM subscription for rewriting their stuff (non-native english speakers) in english. There are many use cases for running good models locally. Maybe not for you, but someone might find this beneficial.

dwa3592··on Codex Micro
Why isn't there a video of it?
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
agreed!! in my heart i really wanted to say by the end of 2026 but wanted to add some wiggle room in case they start to ban open source AI development.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
it's a 16GB machine. i am proud of this machine so far.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
i have been optimizing for that. for now samosa is capped at using half of the avaiable cores and switching between them, which keeps the system 'less hot' as it would have been. i will also release better thermal control in the next release. at this point its basically sacrificing about 20% of the speed to keep the hardware less stressed (and hot).
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
i am working on making it faster but to me 7-9 tokens/sec feels very good. it was 0 tokens/sec a year ago.
dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
>>It's quite telling you didn't use Qwen3.6-35B-A3B locally to build that

that would have run into a race condition unfortunately ;)

but there is a sample landing page + a python function on the repo which shows what the model produced. my goal is to integrate the local model in my workflow so that claude/OAI can call this model for basic stuff.

dwa3592··on Running Gemma 4 26B at 5 tokens/sec on a 13-year-old Xeon with no GPU
I have a prediction. By the mid of 2027, we will have >200B MoE models running on basic consumer hardware.

I am running Qwen3.6-35B-A3B locally on my 16GB mac with 7-9 tokens/second. Link - https://github.com/deepanwadhwa/samosa-chat

This is a GPT4 level model running locally with a decent speed on a 16gb ram macbook air.

dwa3592··on Show HN: Samosa Chat - Run Qwen3.6-35B-A3B Locally on a 16 GB Mac
Thanks for testing. Actually if you open the samosa app; it will show you memory consumption, tokens/sec etc. Let me know what you think.
dwa3592··on The Three-Second Theft: Why AI Voice Fraud Outruns Every Defence
me and my wife made up a word in 2024 for this. the word doesn't exist in any language. we say it to each other all the time. even if i give you the spelling for it, you will say it wrong. i recommend everyone to do something similar. i should do it with my parents too.
dwa3592··on Show HN: Samosa Chat - Run Qwen3.6-35B-A3B Locally on a 16 GB Mac
>>One reason I am not running local models on my Mac now a days, is My Mac book pro is getting heated more

Samosa was optimized for keeping mac's temp in check. This is one of the important reasons for creating this - no excessive wear/tear to the machine. https://github.com/deepanwadhwa/samosa-chat#the-three-princi...

maybe give it a try and let me know if your macbook is getting heated while running this?

dwa3592··on Samosa Chat: Run Qwen3.6-35B-A3B Locally on a 16 GB Mac
i was pleasantly surprised to find out it hadn't been done until now.
dwa3592··on Buried Apple feature turns an iPhone into the perfect kids' dumb phone
my iphone is already kind of dumb. i don't have any social media apps. i have all notifications turned off (except ringtone for call). i only use my phone for calling and texting. it feels very expensive for those 2 operations. but i have the choice of downloading whatever shit i want to download.
dwa3592··on GPT-5.6
This marketing video on the page is nice!! can't wait for the hardware to get cheaper to live the AI life i wanna live.
dwa3592··on AI content is everywhere on social media, especially LinkedIn
What I agree with in this article is that there is shit ton of slop on the internet today. What I disagree with is that if pangram says it's human, then it's not AI. That is hardly the case. Pangram fails spectacularly in detecting AI.

https://github.com/deepanwadhwa/ai_detector_fails/blob/main/... - I posted this link in another thread the other day. I might do more of these tests in the upcoming days and put universal jailbreaks for people to fool these 'AI detectors'.

dwa3592··on Show HN: 18 Words
I like the timer but just give the option - play with timer (pro), play without timer (relax). split the results as well.
dwa3592··on Show HN: Analog Watch
would be nice if the results also showed the analog watch positions.
dwa3592··on We made Grok 4.5, GPT-5.5, and Claude build the same apps
i will give you the remaining 1% because i felt the same way.
dwa3592··on Mistral's Robostral Navigate: a state of the art robotics navigation model
This is very cool. Congratulations to the Mistral team. Map less navigation in the outside world has been around for quite a while. But map less navigation inside the buildings is relatively new. Some stanford researchers trained a vision model (PIGEON) which could tell the geo-location from any image. It was not released publicly due to privacy nightmarish (stalking!) possibilities but I am assuming similar type of tech has gone behind this robot. if someone knows more, feel free to correct.

here's the link to the PIGEON paper - https://lukashaas.github.io/PIGEON-CVPR24/

dwa3592··on Mistral's Robostral Navigate: a state of the art robotics navigation model
maybe it did a cartwheel instead of turning right.
dwa3592··on What Emily Bender meant by "stochastic parrots"
>>Give any LLM the first paragraph of any Wikipedia article - almost certainly in the training set, and uniquely so - and it won't predict the next word correctly, a lot of the time. But it will predict a word that is grammatically correct, stylistically apropos, and most likely factually correct. So what's it really doing, hm?

you are grossly negligent of LLMs are created. I would highly recommend reading about post training, RLHF, alignment etc. First pass of training is literally "predict the next token". That's it. The first pass is also known as pre training. There's a shit ton of work (instructions, tool use, and reasoning etc) that's done afterwards because the pre-trained is model is useless. if you have some free time, I'd recommend doing this course - https://www.deeplearning.ai/courses/post-training-of-llms

dwa3592··on Every new car sold in the European Union must include a driver monitoring camera
>>The worst is the cruise control that tries to stick to the speed limit

is this a feature really? is it only applied in European cars?

dwa3592··on Mapping homes you can buy from the US government for <$100k
not quiet true - if you wanna use the land - you'd have to pay to destroy the house already built on top of it.
dwa3592··on What Emily Bender meant by "stochastic parrots"
>>If someone substituted all of your sensory inputs for something else for your entire life, how would you notice?

I don't know how or if I will notice. That's the biology, chemistry and physics of the brain that I don't know. I hope someone is looking into it. But this does not mean in any way that LLMs are similar to our brains!!!!!! WE DON'T KNOW HOW OUR BRAINS WORK. So going back to language modeling - language models were stochastic in nature when that paper was written, they still are albeit we are trying to make them as deterministic as possible.

dwa3592··on Top researchers leave USA for the Netherlands (in Dutch)
Actually there are many such headlines, just replace the Netherlands with [China, Singapore, Australia, India].
← PreviousPage 2 of 14Next →